Ariel Goldstein

[Ariel Goldstein @GoldsteinYAriel]

In summary, by leveraging naturalistic neural recordings and LLMs, this study identifies a previously unrecognized information-making process in the speaker’s brain. We would like to thank our co-authors: Haocheng Wang, @TomSheffer17807, @DariaLioub, @SchainMariano @HassonLab 🙏

[Ariel Goldstein @GoldsteinYAriel]

We are excited to share our new preprint! 🚨
https://t.co/mRKThbiSbH
In this work, we investigate the neural mechanisms by which speakers generate information-rich linguistic content during spontaneous natural conversation.

[Ariel Goldstein @GoldsteinYAriel]

Finally, turning to LLMs to computationally model this additional processing, we find that improbable words emerge as stable predictions in significantly later layers than probable words, suggesting that information-rich words require deeper internal computation before generation

[Hasson Lab @HassonLab]

How does language learning emerge from everyday experience? Our new preprint, led by @HRaviv830 offers a mechanistic answer.

[Omer Nahum @omer6nahum]

Do LLMs have motivation?
Motivation is a key lens for explaining human behavior.
As LLM behavior becomes more human-like, a natural question arises: could it help understand model behavior too?

With @AsaelSklar @GoldsteinYAriel @roireichart
📄 Paper: https://t.co/cdh2qmGNmE
1/5

[Ariel Goldstein @GoldsteinYAriel]

I’m hiring a PhD student for my lab at Cambridge’s Center for Human Inspired AI (CHIA)! Work at the intersection of AI × cognition × neuroscience.
📅 Deadline: Dec 2
🔗 Program: https://t.co/YaOeZRagPd
📚 My Google Scholar: https://t.co/kOEx7vAmmA

[Daria Lioubashevski @DariaLioub]

🚨 New preprint!
One idea, many ways to say it – does your brain track those options before you speak?
Using LLMs, we put this to the test:
https://t.co/rCRvuPwDtT
We show for the 1st time that the brain represents many alternatives simultaneously in both listening & speaking 🧵

[Ariel Goldstein @GoldsteinYAriel]

Most novel insight:
When an LLM recognizes a bias, it’s actually less likely to exhibit it.
This helps explain conflicting results in prior studies—each was seeing a subset of the broader pattern.

[Ariel Goldstein @GoldsteinYAriel]

New paper out!
Do LLMs Exhibit Human-Like Cognitive Biases?
We systematically tested 20 biases across 10 leading LLMs using pre-registered experiments. The result: cognitive biases in LLMs are both pervasive and nuanced.
https://t.co/BtJt32SOpw

[Amir Taubenfeld @TaubenfeldAmir]

New Preprint 🎉

LLM self-assessment unlocks efficient decoding ✅

Our Confidence-Informed Self-Consistency (CISC) method cuts compute without losing accuracy.

We also rethink confidence evaluation & contribute to the debate on self-verification.

https://t.co/4vSCs9ETPL
1/8👇

[Refael Tikochinski @R_Tikochinski]

Very excited to share our new paper published in Nature Communications @NatureComms (link below). This work is part of my PhD research under the supervision of @roireichart (Technion), @HassonUri (@HassonLab), and @ArielYGoldstein, in collaboration with @YoavMeiri.

[Ariel Goldstein @GoldsteinYAriel]

@yoavgo Second, drawing on our human experience where sometimes (we feel) that humans who talk about an issue/problem can reach a conclusion that separately they couldn't have - worth mimicking no?

[Ariel Goldstein @GoldsteinYAriel]

@yoavgo First, if you are interested in verbal-based interactions, artificial agent systems serve as a "lab" for different hypotheses about language-based interactions.